NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm, #4482 most downloaded on npm
Latest stable
4.0.102
Last release 7 days ago
10 Nov 2026
Ships on a steady schedule
a new release about every 9 days
Most releases are documented
notes for 36 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
688 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
@ai-sdk/provider-utils@4.0.0-beta.26
@ai-sdk/provider-utils@4.0.0-beta.25
Your coding agent can read these notes before it upgrades. Set up the MCP server →
0c3b58b: fix(provider): add specificationVersion to ProviderV3
@ai-sdk/provider-utils@4.0.0-beta.23
@ai-sdk/provider-utils@4.0.0-beta.22
@ai-sdk/provider-utils@4.0.0-beta.21
7c4328e: Adds url-based pdf and image support for anthropic tool results
21f378c: fix(provider/anthropic): do not limit maxTokens when model id is unknown
80894b3: add return file_id property for anthropic code-execution-20250825 to download output files.
file_id property for anthropic code-execution-20250825 to download output files.@ai-sdk/provider-utils@4.0.0-beta.20
0e38a79: support ANTHROPIC_BASE_URL
f4db7b5: feat(provider/anthropic): expose container from response in provider metadata
ca07285: feat(anthropic): add prompt caching validation
9354297: feat(provider/anthropic): add support for Agent Skills
3794514: feat: flexible tool output content support
81d4308: feat(provider/anthropic): mcp connector support
4c5a6be: feat(provider/anthropic): default and limit maxTokens based on model
f33a018: chore: add model ID for Haiku 4.5
@ai-sdk/provider-utils@4.0.0-beta.17
d08308b: feat(provider/anthropic): memory tool
6f845b4: Add support for 2025-08-25 code execution tool
ed537e1: Add support for pdf file in tool result in anthropic
@ai-sdk/provider-utils@4.0.0-beta.16
@ai-sdk/provider-utils@4.0.0-beta.15
@ai-sdk/provider-utils@4.0.0-beta.14
@ai-sdk/provider-utils@4.0.0-beta.13
@ai-sdk/provider-utils@4.0.0-beta.12
9cff587: chore(provider/anthropic): lazy schema loading
95f65c2: chore: use import \* from zod/v4
@ai-sdk/provider-utils@4.0.0-beta.10
@ai-sdk/provider-utils@3.1.0-beta.9
@ai-sdk/provider-utils@3.1.0-beta.8
e8109d3: feat: tool execution approval
dedf206: feat(provider/anthropic): expose stop_sequence in provider metadata
0adc679: feat(provider): shared spec v3
a5a8db4: chore: add model ID for Sonnet 4.5
e1e2821: fix(provider/anthropic): support null title in web fetch tool
10c1322: fix: moved dependency @ai-sdk/test-server to devDependencies
LanguageModelV3@ai-sdk/test-server to devDependencies11e4abe: feat(provider/anthropic): web search tool updates
11e4abe: feat(provider/anthropic): web search tool updates
afb00e3: feat(provider/anthropic): add text_editor_20250728 tool support
Add text_editor_20250728 tool for Claude 4 models (Sonnet 4, Opus 4, Opus 4.1) with optional max_characters parameter and no undo_edit command support.
f6603b7: fix(provider/anthropic): correct raw usage information
fa35e95: feat(provider/anthropic): add web fetch tool
c5440c5: chore(provider/anthropic): update anthropic model ids
4616b86: chore: update zod peer depenedency version
@ai-sdk/provider-utils@3.1.0-beta.3
Provider-V31cad0ab: feat: add provider version to user-agent header
@ai-sdk/test-server@1.0.0-beta.0
78928cb: release: start 5.1 beta
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
f6809e3: fix(workflow): align the prepareStep results of WorkflowAgent with ToolLoopAgent. Returned instructions (or the deprecated system) replace th…
ff89832: fix(workflow): call onAbort instead of onError when a WorkflowAgent call is aborted during a model step with a custom abort reason. generate() still rejects with that reason. stream() now resolves with the steps that finished, as it does for an abort without a reason.
2473a71: fix(workflow): WorkflowAgent uses the last value yielded by an async generator tool as the tool result, like ToolLoopAgent. A generator that throws after yielding produces a tool error.
f43ee39: fix(workflow): log the default step limit warning when WorkflowAgent.generate() stops at the default limit.
7ce7ffc: fix(workflow): log provider warnings in WorkflowAgent
WorkflowAgent.generate() and WorkflowAgent.stream() now log the warnings of every model call through the AI SDK warning logger, like ToolLoopAgent. The AI_SDK_LOG_WARNINGS global controls the output.
f6809e3: fix(workflow): align the prepareStep results of WorkflowAgent with ToolLoopAgent. Returned instructions (or the deprecated system) replace the instructions of the step and carry forward to later steps, returned providerOptions are merged with the agent options, and returned headers are merged over the headers of the call.
9307549: feat(workflow): support experimental_refineToolInput in WorkflowAgent, in the constructor and per call. Refined tool inputs are used for tool execution, step results, callbacks, and the next model call, like in ToolLoopAgent.
bf1dd2a: fix(workflow): WorkflowAgent.stream() keeps the tool call in the step result when the model calls an unknown tool or passes input that does not match the schema. The call is marked invalid and the step has a tool-error part, as in generate() and ToolLoopAgent. The model still receives the error as a tool result.
453d880: fix(workflow): call the onInputAvailable tool hook in stream() when the provider sends a tool call without streaming its input first.
5c0e984: fix(workflow): report the provider name and model ID of the called model in the steps of WorkflowAgent.stream() results, matching ToolLoopAgent and WorkflowAgent.generate()
2559173: feat(workflow): support toolApproval in WorkflowAgent
WorkflowAgent accepts a toolApproval configuration in the constructor and per generate() or stream() call. The configuration takes precedence over a tool's needsApproval setting, and its functions run in workflow context, outside of the durable model steps. Calls that the configuration approves run in the same step, and calls that it denies receive an execution-denied tool result without pausing the workflow.
b9f6c82: feat(workflow): support toolOrder in WorkflowAgent
WorkflowAgent accepts toolOrder in the constructor, per call in generate() and stream(), and from prepareCall and prepareStep. Listed tools are sent first in the listed order, and the remaining tools follow in alphabetical order.
f1de9cb: feat(workflow): support the timeout object in WorkflowAgent
generate() and stream() accept timeout: { totalMs, stepMs, firstChunkMs, chunkMs } in addition to a number. stepMs limits each model call. In stream(), firstChunkMs and chunkMs limit the wait for model output. Invalid timeout values are rejected with an InvalidArgumentError. A timeout now also ends a model step when the provider stream ignores the abort signal.
Updated dependencies [3c09e00]
Updated dependencies [f43ee39]
Updated dependencies [7ce7ffc]
Updated dependencies [f6809e3]
Updated dependencies [2559173]
Updated dependencies [f1de9cb]
b161730: fix(workflow): WorkflowAgent now accepts onError and onAbort in the constructor, like ToolLoopAgent. They are called before the callbacks pas
WorkflowAgent now accepts onError and onAbort in the constructor, like ToolLoopAgent. They are called before the callbacks passed to generate() or stream(). An error thrown by an onError or onAbort callback no longer replaces the error or result of the run.WorkflowAgent no longer receive the system prompt or the assistant message that contains the current tool call in options.messages. The messages passed to onToolExecutionStart and onToolExecutionEnd no longer contain the system prompt either. This matches ToolLoopAgent, generateText, and streamText.model, toolChoice, activeTools, and generation settings returned from prepareStep in WorkflowAgent now apply to the current step only, like in ToolLoopAgent. Before, an override returned for one step stayed in effect for all later steps.WorkflowAgent.stream() now aggregates totalUsage the same way as ToolLoopAgent. Token details such as cached and reasoning tokens are kept, and counts that the provider did not report stay undefined instead of becoming 0.### Patch Changes - Updated dependencies [11323f9] - Updated dependencies [2ebc78b] - Updated dependencies [2ebc78b] - Updated dependencies [cb4fa52]
8549a1d: feat(xai): add safetyIdentifier Responses provider option
Sends safety_identifier with Responses API requests so xAI can attribute a policy violation to one end user, and exposes the echoed value on providerMetadata.xai.safetyIdentifier.
Updated dependencies [49c554d]
Updated dependencies [db18e4f]
Updated dependencies [ce27f15]
Updated dependencies [b753c03]
efd2905: fix(workflow): End the final step's telemetry when streaming stops on a client-side tool, preserving the step span and its model call in the
Updated dependencies [ a1a772f ]
8e40444 : Defer validation schema construction until first use to reduce provider import time.
One column per month.